Uncategorized

An article that originally appeared in Duke Today describes a new AI initiative and accompanying steering committee at Duke University, helmed by Provost Alec D. Gallimore. The initiative, which encompasses the University, the School of Medicine, the School of Law, and many other departments, institutes, and centers, reflects months of development and feedback from academic leadership and faculty experts, including Duke AI Health Director Michael Pencina and Faculty Council member Ricardo Henao. Comprising four major pillars (Life with AI, Trustworthy and Responsible AI, Sustainability in AI, and Advancing Discovery with AI), the initiative is served by a new dedicated website.

READ MORE

Presented by Anthony Sorrentino, MD, Clinical Informatics Fellow at Duke University Health System and Primary Care Doctor at Duke Primary Care Riverview, this session explores the strengths and limitations of clinical registry data in research. While real-world data sources such as EHRs and medical claims are widely used, clinical registries stand out for containing detailed, manually abstracted outcomes data. Dr. Sorrentino discusses the challenges of working with registry data, including siloed storage, limited access, and complex governance. He introduces Duke’s pilot data mart, which links multiple clinical registries with EHR data to enable broader research use, and highlights design strategies, key barriers encountered, and ongoing efforts to transform registry data into a more integrated and accessible research asset. WATCH

The Duke Health team, led by Dr. Ben Goldstein and including Dr. Armando Bedoya, Dr. Michael Cary, Dr. Matt Engelhard, Dr. Chuan Hong, Dr. Rishi Kamaleswaran, and AI Health fellow Scott Sun, traveled to Singapore in April to strengthen partnerships with Duke-NUS Medical School. The team engaged with DAISI (Duke-NUS AI + Medical Sciences Initiative), Duke-NUS leadership, and SingHealth to explore collaborative opportunities. The visit culminated in the Health Data Science Symposium, featuring Dr. Goldstein’s keynote on building successful clinical AI partnerships across research, education, and clinical implementation, followed by individual talks and participation in panel discussions by team members. LEARN MORE

Congratulations to Duke AI Health Faculty Affiliate Monica Agrawal, PhD, on being named a 2025 Whitehead Scholar by the Duke University School of Medicine! The Whitehead Scholar program recognizes and supports outstanding potential in early-career biomedical researchers. Dr. Agrawal, who is an Assistant Professor in Biostatistics and Bioinformatics, Computer Science, and Biomedical Engineering at Duke, is currently focused on the use of large language model AI systems in clinical care and human-AI interactions in healthcare settings. READ MORE

The Duke Health AI Evaluation and Governance (E&G) Program recently debuted its new website, including resources for its Algorithm-Based Clinical Decision Support (ABCDS) Group that were previously housed at Duke AI Health, which served as ABCDS’ administrative home and incubator from 2021 until its launch in 2024. The E&G program, which develops methods and frameworks for testing and overseeing health AI applications, was created to “ensure the reliable selection, development, deployment, and utilization of AI technologies” across Duke Health and the Duke University School of Medicine. VISIT WEBSITE

Many important data elements, such as clinical outcome measures, are contained within decentralized, departmental-specific databases and clinical registries outside the Epic (Maestro Care) system. A project supported by a PCORI capacity-building grant developed the technical capacity to integrate this data and create the interfaces to make it more readily available to researchers and providers. One of the first registries to make use of this integration is the Cancer (Tumor) Registry. This set of data can be accessed from Slicer-Dicer or directly from the CRDM (Clinical Research Data Mart). Integrated cancer registry data can be joined to Maestro Care/Epic data, including patient demographics and diagnostic data.

• Slicer-Dicer Tipsheet: The Cancer Registry Cases Model
• LMS: Cancer Registry Data in Slicer-Dicer

Under the leadership of Duke Health Chief Quality Officer/Chief Medical Officer Richard Shannon, MD, Duke University Health System is one of 42 health systems chosen to participate in the Patient-Centered Outcomes Research Institute (PCORI) Health Systems Implementation Initiative (HSII) in 2023. As a member of this group, DUHS can compete for specific awards on topics relevant to PCORI. Duke’s Mike Smith, MD (Pediatric Infectious Diseases) and Tom LeBlanc, MD (Medicine) recently attended the PCORI HSII Learning Network Meeting in Washington, D.C. During the meeting’s second day, which was focused on specific projects. Dr. Smith, Chief of Pediatric Infectious Diseases at Duke, joined the discussion with 20 other sites participating in the Appropriate Antibiotic Prescribing for Children with Acute Respiratory Tract Infections. This project was funded in January of this year and is currently in the pre-implementation phase. Dr. LeBlanc, who is Chief Patient Experience and Safety Officer for the Duke Cancer Institute and Director of Outcomes Research in the Division of Hematologic Malignancies and Cellular Therapy will serve as principal investigator for Duke’s second HSII implementation project, Monitoring Electronic Patient-Reported Outcomes During Cancer Treatment, which was awarded last month.

Duke AI Health Research Scientist Whitney Welsh, PhD, presented a poster, “Using the Delphi Method to Strategize about Health AI,” at the annual meeting of the Association for Clinical and Translational Science in Washington, D.C. this April. Welsh and co-author Shelley Rusincovitch, AI Health managing director, described the results of a Delphi survey conducted at the Duke Summit on AI for Heath Innovation last October. The survey explored whether a consensus exists regarding the main barriers to innovation in health AI, where there are gaps in education and training in health AI, and where in their workflows organizations should implement AI to see the most immediate impact on productivity. Consensus emerged on all three questions: lack of trust was seen as the single greatest barrier to innovation, experience with implementation as the greatest gap in training, and automating health documentation as the point of most immediate impact.

AI Health Communications Director Jonathan McCall recently took part in a Research Town Hall hosted by Duke’s Office of Scientific Integrity. The panel presentation, moderated by Dr. Monica Lemmon and including McCall, Dr. Jory Weintraub, Hannah Kania, Eric Monson, and Katie Lipe focused on different facets of scientific communication for a variety of potential audiences.

New to AI in healthcare or need a refresher? This accessible session presented by Matt Engelhard, Director of the AI Health Data Science Fellowship Program, and Shelley Rusincovitch, Duke AI Health Managing Director, offers a foundational overview of machine learning and AI tailored for healthcare settings. They explain how AI can be used to analyze medical images, text, and structured data, while also addressing potential risks and ethical considerations. Whether you’re just getting started or looking to reconnect with the basics, it’s a valuable resource—and a great primer ahead of the Duke Machine Learning Summer School 2025: Generative AI (MLSS-GenAI) happening June 2-6, 2025.

LEARN MORE